Objective To develop a bag-valve-mask (BVM) which can automatically squeeze to control the tidal volume, and to explore the effect of its application on mannequins. Methods Based on the original BVM, a BVM which can automatically squeeze and control tidal volume was designed, and 36 medical staffs from The First Affiliated Hospital of Chongqing Medical University were selected to apply this instrument, under the 4 conditions of tidal volume of 400, 500, 600 mL and conventional artificial squeeze breathing apparatus, a single EC technique was used to ventilate each mask on the mannequin for 30 min, and the ventilation success rate and ventilation frequency of each group were compared. Results The ventilation success rate at the same time point of the 3 groups of instruments were significantly higher than that of the manual group (P<0.001); the ventilation frequency at the same time point of the manual group was significantly higher than that of the 3 groups of instruments (P<0.001), and the ventilation frequency at all time points of the manual group was significantly higher than that of 12 times/min. Conclusion The BVM with dynamic squeeze control of tidal volume is an automatic, easy to operate new medical device and can assist the ventilation of the BVM. The initial application on the mannequin has obvious effect, which improves the ventilation quality of the simple ventilator to a certain extent, ensures its safety and effectiveness.

Objective To explore the application of improved YOLOv7 algorithm for the automatic detection and classification of different types of blood cells in blood cell images, to improve the accuracy of blood cell recognition and classification. Methods The swin transformer module was integrated into the YOLOv7, coupled with the adoption of the weighted bidirectional feature pyramid network structure, which enabled the network to acquire and propagate richer feature information. The SCYLLA-IoU loss function was employed to replace the conventional complete IoU loss, resulting in more precise target bounding box localization. Results Experimental evaluations conducted on the BCCD blood cell dataset showcased that the improved YOLOv7 model achieved recognition accuracies of 89.3%, 98.5%, and 91.5% for red blood cells, white blood cells, and platelets, respectively. The mean average precision reached 93.1%, which demonstrated a 2.6% improvement over the original YOLOv7 model. Comparative analysis with other published artificial intelligence-based blood cell detection algorithms revealed the superior accuracy of the proposed algorithm. Conclusion The improved YOLOv7 model proves effective for blood cell recognition and classification tasks, which provides significant value in the domain of blood cell detection.

Objective To address the issue of existing hip joint continuous passive motion (CPM) devices failing to meet the home rehabilitation needs of patients, to develope a new type of home-use lower limb rehabilitation CPM device. Methods A main unit and a hip joint fixation strap were made up of the device. The hip joint fixation strap was controlled by the main unit to perform cyclic motion, facilitating the repetitive flexion and extension of patient’s lower limb joints. The prototype was designed and manufactured according to relevant medical device standards, and its angle parameters, angular velocity, static load, noise, motion cycle, and safety performance were verified. Results The device enabled the acetabulum and femoral head of pediatric patients to undergo repeated flexion and extension within the range of 60°~90° at an angular velocity of 4~8°/s. The structural design and functional parameters of the device met the design objectives and complied with relevant standards. Conclusion The home-use lower limb rehabilitation CPM device developed in this study can meet the home rehabilitation needs of pediatric patients.

Objective Aiming at the problems of slow data processing speed and low diagnostic accuracy of medical equipment, to propose a research method of medical equipment information technology based on radio frequency identification (RFID) technology. Methods RFID positioning technology was used, the ant colony algorithm was integrated into the neural network model of artificial intelligence algorithm, and the accurate positioning of medical instruments was realized. At the same time, the medical equipment fault diagnosis model based on fuzzy theory was used to fuse the extracted fault characteristic signals to judge whether the medical equipment had faults, and the reason of the instrument fault was determined after the decision reasoning of fuzzy theory. Finally, the continuous ant colony algorithm was used to optimize the weight of the neural network model in the artificial intelligence algorithm, and the signal classification strength data collected by the RFID system was used to test the algorithm and train the reflected signal model, aiming at improving the global search efficiency of the algorithm. Results The experimental results showed that the accuracy of the improved artificial intelligence algorithm in the identification, tracking and positioning of medical equipment information was more than 90%, up to 97%. Conclusion This research method can effectively improve the identification and positioning accuracy of medical equipment information, and provide strong support for improving the accuracy of medical diagnosis.

Objective To explore the key factors affecting the stable power output of a semiconductor laser therapy instrument based on a polarization-maintaining fiber temperature sensor and to investigate practical reliability analysis methods for optoelectronic devices in laser therapy system. Methods Based on the reliability block diagram method, reliability (RSL), failure rate (λSL) and average life (LSL) analysis models were established for the optoelectronic devices and their peripheral circuits of the system. The impact of operating environment, operating time (t) and working temperature (T) on the reliability of the system were analyzed. Based on the accelerated life model, the relationships between LSL and T, I, and the interaction between T and I were tested under conditions of room temperature high current (T=25℃, I=2.5 A), high temperature operating current (T=50℃, I=1.5 A), and high temperature high current (T=50℃, I=2.5 A). Results The simulation results showed that λSL increased with the increase of T, LSL decreased with the increase of T, RSL decreased with the increase of T and t. Under the condition of I=1.5 A and T=50℃, the estimated values of λSL, LSL and RSL were 5.229×10-5 1/h, 17824.500 h and 0.11418 respectively. The experimental results show that the LSL were 22873, 17693 and 4780 h respectively, and the experimental test results were basically consistent with the simulation results. Conclusion Based on the method proposed in this study, by combining system architecture, design methods, and usage environment, it is possible to analyze and calculate whether the λSL of the equipment meets the usage standards, which can further predict the RSL and LSL of the equipment, providing data support for design, manufacturing, and clinical use.

Objective To explore the appropriate parameters for the application of spiral tomotherapy (TOMO) in hippocampal protective whole brain radiotherapy in mapping the hippocampus between MRI/CT fusion images and CT images. Methods Data from 66 patients who underwent HP-WBRT at Shaanxi Provincial Cancer Hospital from January 2017 to December 2022 were collected as research objects. Among them, 36 patients had hippocampal delineation based on MRI/CT fusion images, while 30 patients had delineation based on CT images. Different parameter combinations were adjusted, including modulation factor (MF), field width (FW), and pitch (Pitch), to evaluate the target coverage and organ at risk coverage of treatment plans to explore the suitable parameters for TOMO. Results The volume of the hippocampal region delineated based on MRI/CT fusion images (HPL, HPR on both sides) was significantly larger than that delineated based on CT images (P<0.001). The optimal MF for TOMO was 2.7 when using MRI/CT fusion images for hippocampal delineation, and 2.5 when using CT images. The optimal FW for both approaches was 2.5 cm. The optimal Pitch for MRI/CT fusion images was 0.287, while for CT images, both 0.287 and 0.430 met the requirements. Conclusion By comparing different parameter schemes of MRI/CT fusion images and CT mapping of hippocampus, the appropriate parameters of TOMO for hippocampal protective whole brain radiotherapy are obtained, which can provide references for optimizing radiotherapy schemes and improve the accuracy and safety of hippocampal protective whole brain radiotherapy.

Objective To compare the dosimetric differences among hybrid radiotherapy technology, intensity modulated radiotherapy (IMRT), volumetric modulate arc therapy (VMAT), and three-dimensional conformal radiotherapy (3DCRT) in whole brain radiotherapy, and to investigate the feasibility of hybrid radiotherapy technology in whole brain radiotherapy. Methods A total of 25 patients who required whole brain radiotherapy were selected and designed with 3DCRT plan, hybrid plan based on IMRT technology (Hybrid-IMRT), hybrid plan based on VMAT technology (Hybrid-VMAT), IMRT plan, and VMAT plan. The same optimization parameters were all used by the Hybrid-IMRT plan and IMRT plan, as well as the Hybrid-VMAT plan and VMAT plan. 60% of the prescription dose (2400 cGy/20 F) was provided by 3DCRT portion of the two mixed plans, while the remaining 40% of the prescription dose (1600 cGy/20 F) was provided by the IMRT or VMAT portion. The target homogeneity index, conformity index, maximum dose to the target area, monitor unit, and the maximum dose to organs at risk (lenses, eyeballs, optic nerves, optic chiasm, and brainstem) of the five plans were compared. Results All indicators of the five plans met the clinical requirements. The homogeneity of target area, maximum dose point of target area, dose of crystal, optic chiasma and brainstem of Hybrid-IMRT and Hybrid-VMAT plans were better than those of IMRT and VMAT plans, and the differences were statistically significant (P<0.05). Compared with IMRT and VMAT plans, there were significant differences in target conformity and eyeball receptivity (P<0.05). The monitor units of Hybrid IMRT and Hybrid VMAT plans decreased by 60% and 10% respectively compared to IMRT and VMAT plans (P<0.05). Conclusion The parameters of Hybrid-IMRT and Hybrid-VMAT plans can meet the requirements of clinical treatment, with better homogeneity of target area, shorter treatment time, and better protection of endangered organs far away from and within the target area. Therefore, hybrid irradiation technology can be applied to whole brain radiotherapy.

Objective To construct a intensive care information system in response to the clinical management needs of emergency critically ill patients, and to evaluate the effect of its clinical application. Methods The system was oriented to clinical needs, adopted service-oriented architecture design. The server and client were loosely coupled, and the wired-wireless deep integration network architecture was adopted. The system realized the functions of multi-system information sharing, automatic collection and recording of condition data and information visualization. The medical records of 100 patients before and after the system application were selected to analyze and evaluate the effect of the system application. Results After the adoption of the intensive care information system, the time consuming processing of all kinds of medical documents and the length of patients’ ICU stay were significantly shortened (P<0.05); and the satisfaction of medical and nursing staff was significantly increased (P<0.05). Conclusion The intensive care information system based on clinical needs can improve the efficiency of clinical management and has positive significance for improving the quality of clinical management and treatment. The development and application of the system also provides a reference for the construction of various medical information systems.

Objective In order to improve the electronic input efficiency of the handwritten data in paper-based medical equipment quality control testing original record forms, to replace the traditional manual input method, and realize batch automatic entry of handwritten testing data. Methods Based on Python language, an intelligent recognition system for medical equipment quality control testing original record forms based on deep learning optical character recognition (OCR) technology was developed. The deep learning OCR technology used Baidu AI Cloud OCR cloud service. The system could batch recognize electronic images of quality control testing record forms, obtain structured testing data recognition results, and export them to spreadsheets. Results The system has achieved intelligent recognition of 8 common medical equipment quality control testing original record forms. Through experimental tests, the average recognition time of 8 kinds of quality control testing records was 5.45 s, and the average recognition accuracy was 95.94%. After the application of the system, the electronic input time of handwritten data in the original medical equipment quality control testing record form was significantly lower than the traditional manual input method, and the difference was statistically significant (P<0.001). Conclusion The system has fast recognition speed, high recognition accuracy, and achieves batch, intelligent, and electronic data input of medical equipment quality control testing original record forms, which saves a lot of manpower, improves the efficiency of quality control testing data collection and lays a good foundation for quality control testing data analysis.

Objective To solve the problem of information silos in the physical examination management system and explore the standardized and normalized path of physical examination management system construction. Methods The health physical examination management system was designed according to the pre-examination, in-examination, and post-examination processes of physical examination business. According to the hospital information system prescription dictionary definition of physical examination inspection project name and code, the primary index technology was used to directly obtain data from the production system of the main data through the hospital integration platform, and then the clinical data sharing with physical examination data was realized. Results The system achieved the interoperability and standardized management of health examination data for examinees, with both terminal management and process supervision and management needs. It effectively reduced the time required to open orders, pay fees and complete physical examinations, and the differences were statistically significant (P<0.05). It also significantly improved satisfaction among examiners (P<0.001), meeting their expectations for the system. Conclusion The design and application of the system can change the existing health management service mode, which is conducive to the regional radiation and promotion of the system.

Objective To explore the application effectiveness of the intelligent management system in the cardiothoracic intensive care unit (CTICU) to support medical decision-making and personalized medicine. Methods The digital twin repository was constructed by using patient data. The digital twinning (DT) technology was employed to create virtual patient models, and allowed real-time comparison with actual patient data for highly precise monitoring and management. Results The DT technology was introduced to establish an intelligent and humanized CTICU management system. Compared with the traditional ICU, the performance of query response time, data reading and writing was significantly improved (all P<0.05), which provided strong support for medical care and decision-making. Conclusion The development of the CTICU intelligent management system based on DT technology contributes to improving treatment outcomes and patient safety, thereby providing greater support for healthcare teams and driving advancements in the medical field.

Objective To construct a grey GM (1,1) prediction model based on medical index data such as the incidence cases number, average cost, average hospitalization day, drug cost ratio, and material cost ratio for gastric cancer, to analyze the trend of changes in medical business, aiming to provide methodological basis for single-disease management. Methods The grey GM (1,1) prediction model was constructed by using the data of incidence cases number, average cost, average hospitalization day, drug and material cost ratio for gastric cancer in our hospital from 2013 to 2018. Posterior difference ratio C value and small error probability P value were used to evaluate the accuracy of the model, and relative error and rank deviation were used to evaluate the fitting effect of the model. The prediction effect of the grey GM (1,1) model was verified through the data from 2020-2023, and the medical business indicators for 2024-2025 were predicted based on the adjusted model. Results The grey GM (1,1) prediction model constructed in this study performed well in predicting the average cost, average hospitalization day and drug cost ratio. According to this model, it is predicted that by 2025, the average cost, average hospitalization day and drug cost ratio for gastric cancer can be at 71285.56 yuan, 14.22 d and 13.09%, respectively. Conclusion The grey GM (1,1) model can fit well with the changing trends of the average cost, average hospitalization day, and drug cost ratio for gastric cancer. The model predicts that the average cost shows an increasing trend year by year, while the average hospitalization day and the drug cost ratio both show a decreasing trend annually. This model can provide a theoretical basis for medical quality monitoring of single-disease and improving medical operational efficiency.

Objective To explore the implementation effect of SPD management mode in a grade Ⅲ-A hospital in Guangxi, and analyze its effectiveness in improving operational efficiency and reducing the cost of medical consumables, so as to provide an effective way for public hospitals to reduce the cost of medical consumables. Methods Through supplier centralized procurement platform, master data system construction, SPD central database construction, operating room and intervention room construction, a medical consumables SPD comprehensive management model was built. The effect of SPD management was evaluated by comparing the data changes of hospital labor management cost, capital cost, inventory error rate, consumables use efficiency and other dimensions before and after the implementation of SPD management mode. Results After the implementation of SPD management mode, the number of hospital consumables warehouse management personnel (including logistics distribution) was reduced from 72 to 3; personnel management cost decreased by 77.18%, consumables management liquidation process time decreased by 4 d, average monthly inventory capital cost decreased by 97.60%, manual statistical time of nurses decreased by 73.26%, inventory turnover days decreased by 9 d, and claim satisfaction rate increased by 25.70%, the differences were statistically significant (P<0.05). It has achieved refined inventory management, significant cost savings and efficiency improvements. Conclusion SPD management mode can effectively reduce the cost of hospital consumables and improve management efficiency through refined consumables management and data analysis. The successful implementation of SPD management mode has important social significance for improving the management level of public hospitals, and it is worth widely promoting in medical institutions.

Objective To explore the application effects of medical consumables management in pharmacy intravenous admixture services (PIVAS) based on the supply-processing-distribution (SPD) management mode. Methods The SPD management mode was introduced to optimize the traditional management mode and applied to the management of medical consumables in PIVAS. A retrospective analysis was conducted on the management of medical consumables of PIVAS at Hebei Provincial Hospital of Traditional Chinese Medicine in both the traditional management mode (from January to April 2023) and the SPD management mode (from May to August 2023). A comparative observation was made on requisition replenishment time, inventory time, accuracy of accounts, inventory turnover rate, incidence of adverse events and satisfaction of medical staff between the SPD management mode and the traditional management mode. Results Under the SPD management mode, the requisition replenishment time decreased from (51.25±6.29) min to (3.00±1.15) min, and the inventory time decreased from (62.50±9.57) min to (36.25±7.50) min, with both differences being statistically significant (P<0.05); the accuracy of accounts increased from 73.75%±4.79% to 97.00%±1.15%, and the inventory turnover rate increased from 80.00%±4.08% to 92.57%±2.22%, with both differences being statistically significant (P<0.05); compared to the traditional mode, the incidence of adverse events such as quality inconsistency, expiration, backlog, stock shortage in the SPD mode group decreased by 88.23%, and medical staff showed higher satisfaction with the SPD management mode. Conclusion The SPD management mode is well applied in PIVAS consumables management, which improves work efficiency and medical staff satisfaction, reduces the incidence of management adverse events, and realizes fine management of consumables by means of information technology.

Objective To analyze the research progress in the identification of glioma and single brain metastases based on multimodal magnetic resonance imaging (MRI), and obtain the factors of improving accuracy in the identification. Methods Through searching three databases of PubMed, Web of Science and FMRS foreign medical information resource retrieval platform, according to the inclusion and exclusion criteria, a comprehensive analysis was made on data sources, number of patients, MRI equipment, MRI sequence, tumor segmentation software, segmentation methods, segmentation scopes, segmentation types, feature extraction methods, screening methods, machine learning classifiers and optimal machine learning classifiers of the included articles. Results A total of 12 articles were included for analysis. The traditional structural sequences of MRI were selected in most studies, least absolute shrinkage and selection operator was the most selected feature screening methods, and random forest was the machine learning classifier with the most use and the best performance. Conclusion MRI radiomics method shows high accuracy in differentiating glioma from single brain metastasis, which is of great help for clinical decision-making.

Objective To use unique device identification (UDI) to realize the intelligent management of the whole-process of medical consumables, ensure the quality and safety of medical consumables, and improve the management efficiency of medical consumables. Methods Based on the construction of the national UDI system, through software function design and management optimization, an intelligent management scheme for medical consumables based on UDI was established, and UDI was used to open up the whole-process management of medical consumables from production, circulation and use, so as to realize the intelligent management mode of UDI in the whole-process management of medical consumables through one code, the whole-process scanning code and accurate tracing. The use data of high-value medical consumables before and after implementing the intelligent management mode based on UDI in our hospital were selected and analyzed to verify the implementation effect of UDI intelligent management. Results Compared with the traditional management mode, after the implementation of UDI-based intelligent management mode, the dictionary management time of high-value medical consumables was reduced from (12.07±1.90) min to (4.15±0.35) min, and the acceptance management time was reduced from (29.10±6.47) min to (8.14±0.92) min. Billing registration management time was reduced from (10.50±1.22) min to (1.00±0.07) min, closed-loop traceability management time was reduced from (31.31±5.07) min to (5.02±0.82) min, the differences were statistically significant (P<0.05). The acceptance quality and safety of medical consumables were guaranteed, and medical quality and safety was improved. Conclusion The practice and implementation of the whole-process intelligent management mode of medical consumables based on UDI can further improve the precision management level of medical consumables, and also provide reference for the application of UDI in medical institutions.

Objective To investigate the composition of hospitalization costs for patients undergoing coronary stent implantation surgery and the influencing factors, providing a reference for controlling medical expenses, reforming payment and strengthening the management of medical consumables. Methods The data on hospitalization costs for 16810 patients undergoing coronary stent implantation surgery from 2019 to the first half of 2023 in W hospital was selected. Structural variation degree analysis and grey relational analysis methods were used to analyze the proportion changes of various expenses for patients and their correlation with hospitalization costs. Statistical methods were also used to analyze the changes in the consumption of major consumables before and after centralized procurement. Results From 2019 to the first half of 2023, the structural variation contribution rate of consumables expenses to the hospitalization costs of patients undergoing coronary stent implantation surgery was the highest, which was 49.20%. Consumables expenses had the highest correlation with hospitalization costs for patients, at 0.922. In the first half of 2023 compared to 2019, examination fees increased by 81.99%. After centralized procurement, the per capita use of coronary stent increased to 2.13. The monthly average number of patients undergoing coronary stent implantation surgery increased by 66.53%. Conclusion The hospitalization cost of patients undergoing coronary stent implantation surgery decreased significantly after the cancellation of consumables addition and the implementation of centralized procurement policy. Centralized procurement is the internal driving force behind the surge in medical visits. It is suggested that hospitals further control the hospitalization cost of patients by optimizing the prices of medical services, strengthening the management of medical consumables, establishing standardized clinical pathways, and promoting centralized quantity-based procurement policie.

Objective To explore the effectiveness of the whole process information refinement scheme of the supply-processdistribution (SPD) project in the hospital consumables management of Nanjing First Hospital. Methods Based on the analysis of the management status of hospital medical consumables, standard classification coding and unique device identification-centered basic database were established, and SPD mode was adopted, third-party supply chain information management platform was introduced, radio frequency identification technology, intelligent container system, hospital information system medical order scanning code billing and other supporting technologies were adopted to carry out the whole process information and fine management of hospital medical consumables. Before (2020) and after (2022) management, the proportion of 100-yuan consumables, the proportion of highvalue consumables, and the reasonable utilization rate of medical consumables were compared, as well as the time spent by staff in weekly application, receipt, inventory and billing of medical consumables, the capital occupied by weekly inventory data, as well as the number of bar code missing paste, pasting errors and billing errors. Results The percentage of 100-yuan consumables and value consumables after management was significantly lower than that before management, while the qualified rate of medical consumables was higher than that before management (all P<0.05). After management, the weekly time of medical consumables application, receiving, inventory storage and billing of nursing staff was lower than that before management (all P<0.05). The weekly inventory amount of chargeable consumables after management was significantly lower than that before management (P<0.05). After management, the omission rate and error rate of barcode of medical consumables were significantly lower than that before management, and the error rate and omission rate of charge name of medical consumables were significantly lower than that before management (all P<0.05). Conclusion The information refinement scheme of the SPD project can effectively control the proportion of medical consumables in hospitals, improve the reasonable utilization rate of medical consumables, and improve the work efficiency of medical staff, and has good clinical application effect.

Objective To construct a scientific and systematic evaluation index system for clinical trials of medical devices. Methods Based on literature research and expert survey, the importance of each level of indexes in the evaluation system was demonstrated using the Delphi method, and the weights of each level of indexes were determined using the analytic hierarchy process. Results The constructed clinical trial evaluation index system for medical devices included three dimensions: research ability and contribution, research implementation and management, and research output and evaluation. It consisted of 8 secondary indexes, and 22 tertiary indexes, with good expert enthusiasm, authority, and coordination of opinions. Conclusion This study has preliminarily established a comprehensive evaluation index system for clinical trials of medical devices, which has high objectivity and scientificity, and has certain reference value for the clinical trial comprehensive evaluation and scientific supervision of medical devices.

Objective To investigate the effect of silencing Rictor on angiogenesis, tumorigenesis and expression of P4HB/Hedgehog in hepatocellular carcinoma cells in vitro. Methods The hepatocellular carcinoma cells were collected and divided into liver cancer cell group (LC group), liver cancer cell+Rictor-NC group (NC group) and liver cancer cell+siRictor group (SR group). The transfection of each group was observed under fluorescence microscope, and the expression of Rictor was detected by real-time PCR. The ability of the cells to form mimetic vessels was observed by three-dimensional culture, and the tumor-forming ability was observed by tumor-forming assay in nude mice. The angiogenesis related indicators and the expression of P4HB/Hedgehog were detected by western blotting. Results There was no transfection in LC group, but green fluorescence was seen in NC group and SR group, indicating successful transfection; and the transfection rate was above 90%, indicating that the transfected cells were stable. The expression of Rictor mRNA, the number of angiogenesis, tumor growth curve, vascular endothelial growthfactor, P4HB and Hedgehog protein in the SR group were significantly decreased (P<0.05), indicating that Rictor silence can promote apoptosis of hepatocellular carcinoma cells and inhibit tumor formation. Conclusion Silencing Rictor can significantly inhibit the angiogenesis of hepatocellular carcinoma cells in vitro, reduce tumorigenesis in nude mice, and inhibit the expression of P4HB/Hedgehog.

Radiotherapy as a mainstream cancer treatment method, has always been the focus of clinical research in terms of precision, safety, and effectiveness. In recent years, the application of robotic technology in the field of radiotherapy has achieved significant results, especially in critical aspects such as patient positioning, tumor tracking, and dose delivery, showcasing its unique advantages. This article provided a comprehensive overview of the research progress of robotics in the field of radiotherapy, systematically discussing the latest research achievements of robotics in external beam radiotherapy, brachytherapy, radiotherapy positioning assistance, and image-guided radiotherapy, so as to provide reference for the application and development of robotics in radiotherapy.

Colorectal cancer is the third most common cancer in the world, and a good endoscopic screening programme is expected to reduce the morbidity and mortality of colorectal cancer. With the continuous improvement of computer technology and the advent of the big data era, research related to artificial intelligence technology-assisted endoscopic disease diagnosis has flourished. Lesion detection, lesion characterization and computed aid quality improvement in colonoscopy are the main clinical applications of artificial intelligence in gastroenterology, and more evidences have been published so far. This paper introduced commonly used deep learning model architectures, summarized the available clinical evidence for the application of artificial intelligence in colorectal lesion detection and discussed and discussed future directions.

Stereotactic radiotherapy (SRT) is an important mean of treating cancer, and its unique dose accumulation effect maximises the protection of the surrounding normal tissues. With the advancement of technology, SRT continues to achieve innovative advantages, a variety of SRT equipment has been developed, which has been playing an increasingly important role in clinical applications. This paper reviewed the development history of SRT equipment, compared the technical characteristics of existing SRT equipment, summarized the key technologies of SRT equipment, and prospected the development trend of SRT equipment.

Contrast enhancement spectral mammography (CESM) is the use of dual-energy subtraction and contrast enhancement techniques on the basis of traditional mammography to display breast calcification, glandular structure, and intrafocal blood supply. Compared to mammography, quantification method of CESM is emerging as an objective and accurate to diagnose abnormal breasts, to distinguish molecular subtypes of breast cancer and to evaluate response to neoadjuvant chemotherapy. At present, there are many measurement schemes for quantitative methods, and there is no unified standard guide. This paper reviewed the clinical application and research status of CESM quantitative method, aiming to explore the advantages and disadvantages of different computational schemes and provide quantitative basis for clinical diagnosis and prognosis.

The application and innovation of digital technology drive the innovative development of modern stomatology theory and practice. Extended reality (XR) technology is a collective term for virtual reality, augmented reality, and mixed reality, which is the product of the integration of various cutting-edge technologies in modern times. It has been applied and researched in various specialized fields of stomatology, promoting the intelligent, precise, and personalized development of preclinical education and clinical medicine. This paper reviewed the current application status of XR technology in the field of stomatology, discussed its advantages and limitations, and proposed countermeasures needed to improve the practicality of this technology in the future, aiming to provide valuable references for the reform and development of stomatology, promote interdisciplinary cooperation, and advance modern medical progress.

Central nervous system tumors are a common cause of non-accidental death in children. Although surgical treatment combined with radiotherapy and chemotherapy has become more and more standardized, some children with brain tumors still have recurrence, metastasis, postoperative complications, and reduced brain cognitive function after treatment and so on. In order to meet the needs of clinical individualized treatment and further improve the quality of life of children, the prediction model combined with clinical information and radiomics features has been widely used in the preoperative and postoperative evaluation of children with brain tumors, and the artificial intelligence method was used to predict survival rate, postoperative recurrence and metastasis, so as to assist clinical treatment decisions. At present, there have been many studies using this method in adult brain tumors, but the research on children’s brain tumors is still insufficient. This article reviewed the research status and progress of radiomics prediction models in predicting the prognosis of children’s brain tumors in recent years.

In the context of “government support for domestic production, encouragement of innovation, and industry integration”, the research and development speed and market demand advantages of domestic staplers were becoming increasingly apparent under the guidance of national policies. Based on the comprehensive introduction to the basic principles of staplers and combining with market data of domestic staplers, this paper presented the current market share of domestic staplers and compared them with imported staplers, summarized the advantages of domestic staplers in technology and clinical applications. At the same time, through literature review and clinical application research, the technical requirements for the key performance of the staplers were discussed. It was proposed that domestic staplers should be optimized in terms of material selection, product structure, production process, etc., so as to meet the development needs of stable performance and wide application of domestic staplers in clinical applications.

Objective Due to the complexity and variability of fault types in ultrasound diagnostic instruments, considering real-time performance, it is difficult to obtain accurate fault data, and it is subjective to only manually diagnose, resulting in low diagnostic efficiency. In order to improve the accuracy of fault diagnosis for ultrasound diagnostic equipment, to design a rapid diagnosis and emergency maintenance method for imageless faults in ultrasound diagnostic instruments. Methods The real-time monitoring environment was utilized to monitor the application status of ultrasound diagnostic instruments, the time of failure in ultrasound diagnostic instruments was calculated, the fault data was obtained, and their initial features were extracted. By calculating the weight value of fault features, their secondary features were extracted, and then the fault matrix was constructed. The fault diagnosis function was used to diagnose the faults of ultrasound diagnostic instruments. Then the corresponding emergency maintenance plans were proposed based on the diagnosis results, and the rapid diagnosis and emergency maintenance method for imageless faults in ultrasonic diagnostic instruments was completed. Results In the experimental testing, the diagnosis time of rapid diagnosis and emergency maintenance method for imageless faults in ultrasonic diagnostic instruments was only 0.89 ms, with higher diagnostic efficiency. Conclusion By designing rapid diagnosis and emergency maintenance method, the response speed and diagnostic accuracy of ultrasound diagnostic equipment can be improved, thereby optimizing the quality of medical services and providing reliable diagnostic results for patients.